
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt


data = pd.read_csv("data/14100089.csv")
data.head(3)


data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 28512 entries, 0 to 28511
Data columns (total 19 columns):
 #   Column                        Non-Null Count  Dtype  
---  ------                        --------------  -----  
 0   REF_DATE                      28512 non-null  int64  
 1   GEO                           28512 non-null  object 
 2   DGUID                         28512 non-null  object 
 3   Immigrant status              28512 non-null  object 
 4   Country of birth              28512 non-null  object 
 5   Labour force characteristics  28512 non-null  object 
 6   Sex                           28512 non-null  object 
 7   Age group                     28512 non-null  object 
 8   UOM                           28512 non-null  object 
 9   UOM_ID                        28512 non-null  int64  
 10  SCALAR_FACTOR                 28512 non-null  object 
 11  SCALAR_ID                     28512 non-null  int64  
 12  VECTOR                        28512 non-null  object 
 13  COORDINATE                    28512 non-null  object 
 14  VALUE                         27983 non-null  float64
 15  STATUS                        529 non-null    object 
 16  SYMBOL                        0 non-null      float64
 17  TERMINATED                    0 non-null      float64
 18  DECIMALS                      28512 non-null  int64  
dtypes: float64(3), int64(4), object(12)
memory usage: 4.1+ MB


# creating a new dataframe using only needed columns
work_force = pd.read_csv("data/Labour_force_by_country.csv", 
                  usecols=["REF_DATE", "Immigrant status", "Country of birth", 
                          "Labour force characteristics", "Sex", "Age group", "VALUE", "UOM", "SCALAR_FACTOR"])

work_force.head(3)


# let's set index to date to avoid reseting every time 
work_force.set_index('REF_DATE', inplace=True)


#-- We set up the first labour force characteristic. We don't need data from the entire population here
employment_rate = work_force.loc[(work_force["Labour force characteristics"] == 'Employment rate') & 
                                   (work_force['Sex']=='Both sexes') & 
                                   (work_force['Age group']=='15 years and over') & 
                                   (work_force['Immigrant status']=='Landed immigrants')]
#employment_rate.head()

#-- what we need so fare
print(employment_rate[['Country of birth', 'VALUE']].head())

          Country of birth  VALUE
REF_DATE                         
2006      Total population   57.3
2006         North America   60.7
2006         Latin America   67.3
2006                Europe   49.8
2006                Africa   59.6


employ_rate_by_country = pd.pivot_table(employment_rate, values='VALUE', index=['REF_DATE'], 
                                       columns=['Country of birth'])
employ_rate_by_country.head()


employ_rate_by_country.loc[2021].plot(kind='bar',stacked=False,figsize=(12, 6))

plt.title('Employment rate by country in 2021')
plt.ylabel('Employment rate(%)')
plt.xlabel('Country')

plt.show()


#work_force.set_index('REF_DATE', inplace=True)
labour_force = work_force.loc[(work_force["Labour force characteristics"] == 'Labour force') & 
                                (work_force['Sex']=='Both sexes') & 
                                (work_force['Age group']=='15 years and over') & 
                                (work_force['Immigrant status']=='Landed immigrants')]

# Labour force by country in 2021
lf_by_country = labour_force.loc[2021, ['Country of birth', 'VALUE']]

# we can reset the index and drop total population
lfc_data = lf_by_country[lf_by_country['Country of birth'] != 'Total population']
lfc_data.reset_index(drop=True, inplace=True)

lfc_data


import folium
import json

# Getting both data ready
with open ('World_Continents.geojson', 'r') as jsonFile:
    geodata = json.load(jsonFile)

lfc_data = lfc_data[lfc_data['Country of birth'] != 'North America'].replace('Latin America', 'South America')
#lfc_data


m = folium.Map(location=[-30, 50], zoom_start=2)

folium.Choropleth(
    geo_data=geodata,
    name="choropleth",
    data=lfc_data,
    columns=["Country of birth", "VALUE"],
    key_on="feature.properties.CONTINENT",
    fill_color="RdYlGn",
    fill_opacity=0.9,
    line_opacity=0.2,
    legend_name='Distribution of labour force (in Thousands) of immigrants in Canada by continent of origin in 2021',
).add_to(m)

folium.LayerControl().add_to(m)

# Display 
m


unemployment_rate = work_force.loc[(work_force['Age group']=='15 years and over') &
                                    (work_force['Country of birth'] == 'Total population')&
                                    (work_force['Labour force characteristics'] == 'Unemployment rate') &
                                    (work_force['Sex'] != 'Both sexes')]

unemployment_rate = unemployment_rate.loc[2021, ['Immigrant status', 'Sex', 'VALUE']]
unemployment_rate.set_index('Immigrant status', inplace=True)


unemploy_rate_pivot = pd.pivot_table(unemployment_rate, values='VALUE', index=['Immigrant status'], 
                                      columns=['Sex'])

unemploy_rate_pivot


unemploy_rate_pivot.plot(kind='bar',stacked=False,figsize=(20, 10))

plt.title('Unemployment rate base on gender and immigration status in 2021')
plt.ylabel('Unemployment rate (%)')
plt.xlabel('Immigration Status')

plt.show()

Country of birth	Africa	Asia	Europe	Latin America	North America	Total population
REF_DATE
2006	59.6	60.7	49.8	67.3	60.7	57.3
2007	61.3	61.5	50.1	64.4	61.2	57.6
2008	61.6	61.1	49.3	64.1	62.0	57.3
2009	60.9	58.9	48.3	62.6	55.6	55.6
2010	61.9	58.7	49.4	61.3	58.3	56.0

Sex	Females	Males
Immigrant status
Born in Canada	6.5	7.6
Immigrants, landed 5 or less years earlier	13.0	7.3
Immigrants, landed more than 10 years earlier	7.9	7.8
Immigrants, landed more than 5 to 10 years earlier	10.2	9.3
Landed immigrants	9.0	8.0
Total population	7.2	7.7

Workforce of immigrants in Canada

Project Overview¶

1. Data pre-processing¶

1.1. Exploration¶

1.2. Cleaning¶

2. Employment rate of immigrants by Country in 2021¶

3. Greographic distribution of labour force by continent of origin¶

First we prepare the data¶

Now we get the geographical data¶

4. Unemployment rate in 2021¶

Observations:¶

	REF_DATE	GEO	DGUID	Immigrant status	Country of birth	Labour force characteristics	Sex	Age group	UOM	UOM_ID	SCALAR_FACTOR	SCALAR_ID	VECTOR	COORDINATE	VALUE	STATUS	SYMBOL	TERMINATED	DECIMALS
0	2006	Canada	2016A000011124	Total population	Total population	Population	Both sexes	15 years and over	Persons	249	thousands	3	v53056904	1.1.1.1.1.1	26121.7	NaN	NaN	NaN	1
1	2006	Canada	2016A000011124	Total population	Total population	Population	Both sexes	25 to 54 years	Persons	249	thousands	3	v53056905	1.1.1.1.1.2	14115.7	NaN	NaN	NaN	1
2	2006	Canada	2016A000011124	Total population	Total population	Population	Males	15 years and over	Persons	249	thousands	3	v53056906	1.1.1.1.2.1	12854.2	NaN	NaN	NaN	1

	Country of birth	VALUE
0	North America	150.7
1	Latin America	612.2
2	Europe	1015.0
3	Africa	597.7
4	Asia	3059.3